< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 36 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')



Text #0

Max Range: 3.2751. Min Range: -3.2751

Max Act: 3.2751. Min Act: -0.1700

Data Index: 4156898 (The Pile)

Max Activating Token Index: 809

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.2751. Min Range: -3.2751

Max Act: 3.2751. Min Act: -0.1700

Data Index: 9720720 (The Pile)

Max Activating Token Index: 835

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.2751. Min Range: -3.2751

Max Act: 3.2751. Min Act: -0.1700

Data Index: 107397 (The Pile)

Max Activating Token Index: 657

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.2751. Min Range: -3.2751

Max Act: 3.2594. Min Act: -0.1700

Data Index: 8247160 (The Pile)

Max Activating Token Index: 694

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.2751. Min Range: -3.2751

Max Act: 3.2437. Min Act: -0.1700

Data Index: 4973664 (The Pile)

Max Activating Token Index: 500

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.2751. Min Range: -3.2751

Max Act: 3.2437. Min Act: -0.1700

Data Index: 3113345 (The Pile)

Max Activating Token Index: 227

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.2751. Min Range: -3.2751

Max Act: 3.2437. Min Act: -0.1700

Data Index: 10334904 (The Pile)

Max Activating Token Index: 220

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.2751. Min Range: -3.2751

Max Act: 3.2437. Min Act: -0.1700

Data Index: 7509728 (The Pile)

Max Activating Token Index: 338

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.2751. Min Range: -3.2751

Max Act: 3.2437. Min Act: -0.1700

Data Index: 7121920 (The Pile)

Max Activating Token Index: 804

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.2751. Min Range: -3.2751

Max Act: 3.2280. Min Act: -0.1700

Data Index: 9851394 (The Pile)

Max Activating Token Index: 359

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.2751. Min Range: -3.2751

Max Act: 3.2280. Min Act: -0.1700

Data Index: 3903533 (The Pile)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.2751. Min Range: -3.2751

Max Act: 3.2280. Min Act: -0.1700

Data Index: 1524892 (The Pile)

Max Activating Token Index: 587

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.2751. Min Range: -3.2751

Max Act: 3.2122. Min Act: -0.1700

Data Index: 6698628 (The Pile)

Max Activating Token Index: 957

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.2751. Min Range: -3.2751

Max Act: 3.2122. Min Act: -0.1700

Data Index: 1411091 (The Pile)

Max Activating Token Index: 973

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.2751. Min Range: -3.2751

Max Act: 3.2122. Min Act: -0.1700

Data Index: 6137687 (The Pile)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.2751. Min Range: -3.2751

Max Act: 3.2122. Min Act: -0.1700

Data Index: 8603357 (The Pile)

Max Activating Token Index: 403

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.2751. Min Range: -3.2751

Max Act: 3.1965. Min Act: -0.1700

Data Index: 2744159 (The Pile)

Max Activating Token Index: 603

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.2751. Min Range: -3.2751

Max Act: 3.1965. Min Act: -0.1700

Data Index: 8285400 (The Pile)

Max Activating Token Index: 850

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.2751. Min Range: -3.2751

Max Act: 3.1965. Min Act: -0.1700

Data Index: 320977 (The Pile)

Max Activating Token Index: 795

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.2751. Min Range: -3.2751

Max Act: 3.1965. Min Act: -0.1700

Data Index: 6340655 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #19